Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/wangke19/gemini-ai-helpersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/wangke19/gemini-ai-helpers/expand-test-case)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/expand-test-case"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/expand-test-case/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/expand-test-case"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/expand-test-case.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.00906 |
| Opus 5 | $0.00011 | $0.00453 |
| Sonnet 5 | $0.00004 | $0.00181 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
expand-test-case scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
openshift:expand-test-case
Synopsis
/openshift:expand-test-case [test-idea-or-file-or-commands] [format]
Description
The expand-test-case command transforms basic test ideas or existing oc commands into comprehensive test scenarios. It accepts three types of input:
- Test idea: Simple description of what to test (e.g., "verify pod deployment")
- File path: Path to existing test file to expand (e.g.,
/path/to/test.shor/path/to/test.go) - oc commands: Direct oc CLI commands to analyze and expand (e.g.,
oc create pod nginx)
The command expands the input to cover positive flows, negative scenarios, edge cases, and boundary conditions, helping QE engineers ensure thorough test coverage.
Supports two output formats:
- oc CLI: Shell scripts with oc commands for manual or automated execution
- Ginkgo: Go test code using Ginkgo/Gomega framework for E2E tests
Implementation
The command analyzes the input and generates comprehensive scenarios:
- Parse Input: Determine if input is a test idea, file path, or oc commands
- If file path: Read and analyze existing test code
- If oc commands: Parse commands to understand what's being tested
- If test idea: Understand the core feature or behavior
- Identify Test Dimensions: Determine coverage aspects (functionality, security, performance, edge cases)
- Generate Positive Tests: Happy path scenarios where everything works
- Generate Negative Tests: Error handling, invalid inputs, permission issues
- Add Edge Cases: Boundary values, race conditions, resource limits
- Define Validation: Clear success criteria and assertions
- Format Output: Generate in requested format (oc CLI or Ginkgo) - MUST follow the standards in "Test Coverage Guidelines" section below
CRITICAL: All generated test scenarios MUST adhere to the coverage dimensions, best practices, and standards defined in the "Test Coverage Guidelines" section below. Use the referenced examples and patterns from OpenShift origin repository.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 80 lines · 22 tokens per session scan A 67f1690e24ac
expand-test-case is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 906 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
bmad-qa-generate-e2e-tests
Generate automated API and end-to-end tests for implemented features. Use when the user says "create qa automated tests for [feature]".
test
Write tests before implementation using Red-Green-Refactor.
paul:verify
Guide manual user acceptance testing of recently built features.
fix-flaky
Analyze and fix flaky (intermittently failing) Playwright tests. Identifies race conditions, improves waiting strategies, and ensures test stability.
tester
Comprehensive testing with parallel execution capabilities.
checklist
Generate a custom checklist for the current feature based on user requirements.